携带自定义 User-Agent
import urllib.request
url = "http://www.baidu.com"
headers = {
"User-Agent" : "Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1"
}
request = urllib.request.Request(url,headers=headers)
resp = urllib.request.urlopen(request)
print(resp.read())
urllib 请求参数 & URL 编码
import urllib.request
import urllib.parse
url = "http://www.baidu.com/s?"
wd = input('请输入查询关键词:')
query = {
"wd":wd
}
query_str = urllib.parse.urlencode(query)
headers = {
"User-Agent" : "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.170 Safari/537.36"
}
request = urllib.request.Request(url + query_str,headers=headers)
resp = urllib.request.urlopen(request)
print(resp.read())
urllib 写入文件
import urllib.request
import urllib.parse
url = "http://www.baidu.com/s?"
wd = input('请输入查询关键词:')
query = {
"wd":wd
}
query_str = urllib.parse.urlencode(query)
headers = {
"User-Agent" : "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.170 Safari/537.36"
}
request = urllib.request.Request(url + query_str,headers=headers)
resp = urllib.request.urlopen(request)
resp_str = resp.read().decode('utf-8')
with open('sample04_2.html','w',encoding='utf-8') as f:
f.write(resp_str)